The importance of production from Shale and its impact on the total US energy equation has focused much attention on this prolific source of hydrocarbon. Consequently, research related to unconventional reservoirs has increased significantly in order to better understand the inherent complexities of their behavior. Analytical, numerical and statistical analyses have been applied to large multi-variable data set from Shale assets with different degrees of success. The notion that shale is a “statistical play” may be attributed to the fact that many of our preconceived notions on storage and flow mechanisms in shale are not supported by facts. Therefore, we set out to examine the possibility of learning from the data in order to be able to answer some of the questions that rise during the production process. Data Driven Analytics, having roots in pattern recognition and machine learning, have proven to be capable of extracting useful information from large data sets and are extensively used in many industries. Their application to multivariable data sets from Shale assets, in order to extract understandable structure in the data, is the subject of the work being presented here. This paper presents a Data Driven Analytics study of design parameters such as well trajectories, completion, and hydraulic fracturing variables for a large number of horizontal wells in Marcellus Shale. The data set from the Shale assets is so complex that use of conventional statistical analysis does not results in understandable trends and patterns. On the other hand, when advanced pattern recognition tools are used, certain (previously hidden) patterns emerges from the data with unmistakable trends. In this article impact of parameters such as up-dip versus down dip deviation of wells, stimulated lateral length and cluster spacing, etc. on production from wells in a Shale asset is analyzed using an advance pattern recognition algorithm. The analyses are performed using production from multiple time intervals throughout the life of wells.
[1]
Shahab D. Mohaghegh,et al.
Which Parameters Control Production in Shale Assets? A Pattern Recognition Study
,
2013
.
[2]
Yueming Cheng.
Impact of Water Dynamics in Fractures on the Performance of Hydraulically Fractured Wells in Gas-Shale Reservoirs
,
2012
.
[3]
Randy Lafollette,et al.
Practical Data Mining: Analysis of Barnett Shale Production Results With Emphasis on Well Completion and Fracture Stimulation
,
2012
.
[4]
Robert F. Shelley,et al.
Data Analysis of Barnett Shale Completions
,
2008
.
[5]
Randy F. LaFollette,et al.
Practical Data Mining: Lessons-Learned From the Barnett Shale of North Texas
,
2011
.
[6]
Yueming Cheng,et al.
Impacts of the Number of Perforation Clusters and Cluster Spacing on Production Performance of Horizontal Shale-Gas Wells
,
2012
.
[7]
Shahab D. Mohaghegh,et al.
Virtual-Intelligence Applications in Petroleum Engineering: Part 3—Fuzzy Logic
,
2000
.